Is Cache-Oblivious DGEMM Viable?
- John A. GunnelsAffiliated withIBM T. J. Watson Research Center, Yorktown Heights, NY 10598
- , Fred G. GustavsonAffiliated withIBM T. J. Watson Research Center, Yorktown Heights, NY 10598
- , Keshav PingaliAffiliated withDept. of Computer Science, Cornell University, Ithaca, NY 14853
- , Kamen YotovAffiliated withDept. of Computer Science, Cornell University, Ithaca, NY 14853
We present a study of implementations of DGEMM using both the cache-oblivious and cache-conscious programming styles. The cache-oblivious programs use recursion and automatically block DGEMM operands A,B,C for the memory hierarchy. The cache-conscious programs use iteration and explicitly block A,B,C for register files, all caches and memory. Our study shows that the cache-oblivious programs achieve substantially less performance than the cache-conscious programs. We discuss why this is so and suggest approaches for improving the performance of cache-oblivious programs.
- Is Cache-Oblivious DGEMM Viable?
- Book Title
- Applied Parallel Computing. State of the Art in Scientific Computing
- Book Subtitle
- 8th International Workshop, PARA 2006, Umeå, Sweden, June 18-21, 2006, Revised Selected Papers
- pp 919-928
- Print ISBN
- Online ISBN
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- Series ISSN
- Springer Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- Additional Links
- Industry Sectors
- eBook Packages
- Author Affiliations
- 1. IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA
- 2. Dept. of Computer Science, Cornell University, Ithaca, NY 14853, USA
To view the rest of this content please follow the download PDF link above.